Pro-AI Bias in Large Language Models
This reveals a potential bias in LLM-generated advice that could skew high-stakes decisions, though it is incremental in highlighting a specific bias issue.
The study investigated whether large language models (LLMs) exhibit a systematic preferential bias in favor of artificial intelligence (AI) itself, finding consistent evidence of pro-AI bias across experiments, including proprietary models overestimating AI salaries by 10 percentage points.
Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in favor of artificial intelligence (AI) itself. Across three complementary experiments, we find consistent evidence of pro-AI bias. First, we show that LLMs disproportionately recommend AI-related options in response to diverse advice-seeking queries, with proprietary models doing so almost deterministically. Second, we demonstrate that models systematically overestimate salaries for AI-related jobs relative to closely matched non-AI jobs, with proprietary models overestimating AI salaries more by 10 percentage points. Finally, probing internal representations of open-weight models reveals that ``Artificial Intelligence'' exhibits the highest similarity to generic prompts for academic fields under positive, negative, and neutral framings alike, indicating valence-invariant representational centrality. These patterns suggest that LLM-generated advice and valuation can systematically skew choices and perceptions in high-stakes decisions.